refs.bib

@article{gal2022image,
  title={An image is worth one word: Personalizing text-to-image generation using textual inversion},
  author={Gal, Rinon and Alaluf, Yuval and Atzmon, Yuval and Patashnik, Or and Bermano, Amit H and Chechik, Gal and Cohen-Or, Daniel},
  journal={arXiv preprint arXiv:2208.01618},
  year={2022}
}

@article{imagen,
  title={Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding},
  author={Saharia, Chitwan and Chan, William and Saxena, Saurabh and Li, Lala and Whang, Jay and Denton, Emily and Ghasemipour, Seyed Kamyar Seyed and Ayan, Burcu Karagol and Mahdavi, S Sara and Lopes, Rapha Gontijo and others},
  journal={arXiv preprint arXiv:2205.11487},
  year={2022}
}

@article{parti,
  title={Scaling autoregressive models for content-rich text-to-image generation},
  author={Yu, Jiahui and Xu, Yuanzhong and Koh, Jing Yu and Luong, Thang and Baid, Gunjan and Wang, Zirui and Vasudevan, Vijay and Ku, Alexander and Yang, Yinfei and Ayan, Burcu Karagol and others},
  journal={arXiv preprint arXiv:2206.10789},
  year={2022}
}

@article{dreambooth,
  title={Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation},
  author={Ruiz, Nataniel and Li, Yuanzhen and Jampani, Varun and Pritch, Yael and Rubinstein, Michael and Aberman, Kfir},
  journal={arXiv preprint arXiv:2208.12242},
  year={2022}
}

@article{imagic,
  title={Imagic: Text-based real image editing with diffusion models},
  author={Kawar, Bahjat and Zada, Shiran and Lang, Oran and Tov, Omer and Chang, Huiwen and Dekel, Tali and Mosseri, Inbar and Irani, Michal},
  journal={arXiv preprint arXiv:2210.09276},
  year={2022}
}

@article{prompttoprompt,
  title={Prompt-to-prompt image editing with cross attention control},
  author={Hertz, Amir and Mokady, Ron and Tenenbaum, Jay and Aberman, Kfir and Pritch, Yael and Cohen-Or, Daniel},
  journal={arXiv preprint arXiv:2208.01626},
  year={2022}
}

@inproceedings{clip,
  title={Learning transferable visual models from natural language supervision},
  author={Radford, Alec and Kim, Jong Wook and Hallacy, Chris and Ramesh, Aditya and Goh, Gabriel and Agarwal, Sandhini and Sastry, Girish and Askell, Amanda and Mishkin, Pamela and Clark, Jack and others},
  booktitle={International Conference on Machine Learning},
  pages={8748--8763},
  year={2021},
  organization={PMLR}
}

@article{dalle2,
  title={Hierarchical text-conditional image generation with clip latents},
  author={Ramesh, Aditya and Dhariwal, Prafulla and Nichol, Alex and Chu, Casey and Chen, Mark},
  journal={arXiv preprint arXiv:2204.06125},
  year={2022}
}

@article{glide,
  title={Glide: Towards photorealistic image generation and editing with text-guided diffusion models},
  author={Nichol, Alex and Dhariwal, Prafulla and Ramesh, Aditya and Shyam, Pranav and Mishkin, Pamela and McGrew, Bob and Sutskever, Ilya and Chen, Mark},
  journal={arXiv preprint arXiv:2112.10741},
  year={2021}
}

@inproceedings{maskgit,
  title={Maskgit: Masked generative image transformer},
  author={Chang, Huiwen and Zhang, Han and Jiang, Lu and Liu, Ce and Freeman, William T},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={11315--11325},
  year={2022}
}

@inproceedings{ldm,
  title={High-resolution image synthesis with latent diffusion models},
  author={Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj{\"o}rn},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={10684--10695},
  year={2022}
}

@article{vaswani2017attention,
  title={Attention is all you need},
  author={Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and Kaiser, {\L}ukasz and Polosukhin, Illia},
  journal={Advances in neural information processing systems},
  volume={30},
  year={2017}
}

@article{goodfellow2020generative,
  title={Generative adversarial networks},
  author={Goodfellow, Ian and Pouget-Abadie, Jean and Mirza, Mehdi and Xu, Bing and Warde-Farley, David and Ozair, Sherjil and Courville, Aaron and Bengio, Yoshua},
  journal={Communications of the ACM},
  volume={63},
  number={11},
  pages={139--144},
  year={2020},
  publisher={ACM New York, NY, USA}
}

@article{vqvae,
  title={Neural discrete representation learning},
  author={Van Den Oord, Aaron and Vinyals, Oriol and others},
  journal={Advances in neural information processing systems},
  volume={30},
  year={2017}
}

@article{tsimpoukelli2021multimodal,
  title={Multimodal few-shot learning with frozen language models},
  author={Tsimpoukelli, Maria and Menick, Jacob L and Cabi, Serkan and Eslami, SM and Vinyals, Oriol and Hill, Felix},
  journal={Advances in Neural Information Processing Systems},
  volume={34},
  pages={200--212},
  year={2021}
}

@misc{davinciwiki,
    author = "{Wikipedia contributors}",
    title = "Leonardo da Vinci --- {Wikipedia}{,} The Free Encyclopedia",
    year = "2022",
    url = "https://en.wikipedia.org/w/index.php?title=Leonardo_da_Vinci&oldid=1120869946",
    note = "[Online; accessed 17-November-2022]"
  }
  
@misc{midjourney,
    author = "Midjourney",
    title = "Midjourney",
    url = "https://www.midjourney.com",
    year = 2022
  }

@article{ddpm,
  title={Denoising diffusion probabilistic models},
  author={Ho, Jonathan and Jain, Ajay and Abbeel, Pieter},
  journal={Advances in Neural Information Processing Systems},
  volume={33},
  pages={6840--6851},
  year={2020}
}

@article{bert,
  title={Bert: Pre-training of deep bidirectional transformers for language understanding},
  author={Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
  journal={arXiv preprint arXiv:1810.04805},
  year={2018}
}

@InProceedings{MAE,
    author    = {He, Kaiming and Chen, Xinlei and Xie, Saining and Li, Yanghao and Doll\'ar, Piotr and Girshick, Ross},
    title     = {Masked Autoencoders Are Scalable Vision Learners},
    booktitle = "cvpr",
    month     = {June},
    year      = {2022},
    pages     = {16000-16009}
}

@article{t5xxl,
  title={Exploring the limits of transfer learning with a unified text-to-text transformer.},
  author={Raffel, Colin and Shazeer, Noam and Roberts, Adam and Lee, Katherine and Narang, Sharan and Matena, Michael and Zhou, Yanqi and Li, Wei and Liu, Peter J and others},
  journal={J. Mach. Learn. Res.},
  volume={21},
  number={140},
  pages={1--67},
  year={2020}
}

@article{laion,
  title={Laion-400m: Open dataset of clip-filtered 400 million image-text pairs},
  author={Schuhmann, Christoph and Vencu, Richard and Beaumont, Romain and Kaczmarczyk, Robert and Mullis, Clayton and Katta, Aarush and Coombes, Theo and Jitsev, Jenia and Komatsuzaki, Aran},
  journal={arXiv preprint arXiv:2111.02114},
  year={2021}
}

@article{schuhmann2022laion,
  title={Laion-5b: An open large-scale dataset for training next generation image-text models},
  author={Schuhmann, Christoph and Beaumont, Romain and Vencu, Richard and Gordon, Cade and Wightman, Ross and Cherti, Mehdi and Coombes, Theo and Katta, Aarush and Mullis, Clayton and Wortsman, Mitchell and others},
  journal={arXiv preprint arXiv:2210.08402},
  year={2022}
}

@article{ho2022classifier,
  title={Classifier-free diffusion guidance},
  author={Ho, Jonathan and Salimans, Tim},
  journal={arXiv preprint arXiv:2207.12598},
  year={2022}
}

@article{fid,
  title={Gans trained by a two time-scale update rule converge to a local nash equilibrium},
  author={Heusel, Martin and Ramsauer, Hubert and Unterthiner, Thomas and Nessler, Bernhard and Hochreiter, Sepp},
  journal={Advances in neural information processing systems},
  volume={30},
  year={2017}
}

@inproceedings{coco,
  title={Microsoft coco: Common objects in context},
  author={Lin, Tsung-Yi and Maire, Michael and Belongie, Serge and Hays, James and Perona, Pietro and Ramanan, Deva and Doll{\'a}r, Piotr and Zitnick, C Lawrence},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

@inproceedings{sharma2018conceptual,
  title={Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning},
  author={Sharma, Piyush and Ding, Nan and Goodman, Sebastian and Soricut, Radu},
  booktitle={Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  pages={2556--2565},
  year={2018}
}

@article{merullo2022linearly,
  title={Linearly Mapping from Image to Text Space},
  author={Merullo, Jack and Castricato, Louis and Eickhoff, Carsten and Pavlick, Ellie},
  journal={arXiv preprint arXiv:2209.15162},
  year={2022}
}

@inproceedings{esser2021taming,
  title={Taming transformers for high-resolution image synthesis},
  author={Esser, Patrick and Rombach, Robin and Ommer, Bjorn},
  booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
  pages={12873--12883},
  year={2021}
}

@inproceedings{zhang2021cross,
  title={Cross-modal contrastive learning for text-to-image generation},
  author={Zhang, Han and Koh, Jing Yu and Baldridge, Jason and Lee, Honglak and Yang, Yinfei},
  booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
  pages={833--842},
  year={2021}
}

@inproceedings{karras2019style,
  title={A style-based generator architecture for generative adversarial networks},
  author={Karras, Tero and Laine, Samuli and Aila, Timo},
  booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
  pages={4401--4410},
  year={2019}
}

@article{rolfe2016discrete,
  title={Discrete variational autoencoders},
  author={Rolfe, Jason Tyler},
  journal={arXiv preprint arXiv:1609.02200},
  year={2016}
}

@article{yu2021vector,
  title={Vector-quantized image modeling with improved vqgan},
  author={Yu, Jiahui and Li, Xin and Koh, Jing Yu and Zhang, Han and Pang, Ruoming and Qin, James and Ku, Alexander and Xu, Yuanzhong and Baldridge, Jason and Wu, Yonghui},
  journal={arXiv preprint arXiv:2110.04627},
  year={2021}
}

@article{brock2018large,
  title={Large scale GAN training for high fidelity natural image synthesis},
  author={Brock, Andrew and Donahue, Jeff and Simonyan, Karen},
  journal={arXiv preprint arXiv:1809.11096},
  year={2018}
}

@article{donahue2019large,
  title={Large scale adversarial representation learning},
  author={Donahue, Jeff and Simonyan, Karen},
  journal={Advances in neural information processing systems},
  volume={32},
  year={2019}
}

@article{ho2022video,
  title={Video diffusion models},
  author={Ho, Jonathan and Salimans, Tim and Gritsenko, Alexey and Chan, William and Norouzi, Mohammad and Fleet, David J},
  journal={arXiv preprint arXiv:2204.03458},
  year={2022}
}

@article{kingma2021variational,
  title={Variational diffusion models},
  author={Kingma, Diederik and Salimans, Tim and Poole, Ben and Ho, Jonathan},
  journal={Advances in neural information processing systems},
  volume={34},
  pages={21696--21707},
  year={2021}
}

@inproceedings{lezama2022improved,
  title={Improved masked image generation with token-critic},
  author={Lezama, Jos{\'e} and Chang, Huiwen and Jiang, Lu and Essa, Irfan},
  booktitle={European Conference on Computer Vision},
  pages={70--86},
  year={2022},
  organization={Springer}
}

@article{li2022mage,
  title={MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis},
  author={Li, Tianhong and Chang, Huiwen and Mishra, Shlok Kumar and Zhang, Han and Katabi, Dina and Krishnan, Dilip},
  journal={arXiv preprint arXiv:2211.09117},
  year={2022}
}

@article{brown2020language,
  title={Language models are few-shot learners},
  author={Brown, Tom and Mann, Benjamin and Ryder, Nick and Subbiah, Melanie and Kaplan, Jared D and Dhariwal, Prafulla and Neelakantan, Arvind and Shyam, Pranav and Sastry, Girish and Askell, Amanda and others},
  journal={Advances in neural information processing systems},
  volume={33},
  pages={1877--1901},
  year={2020}
}

@article{radford2019language,
  title={Language models are unsupervised multitask learners},
  author={Radford, Alec and Wu, Jeffrey and Child, Rewon and Luan, David and Amodei, Dario and Sutskever, Ilya and others},
  journal={OpenAI blog},
  volume={1},
  number={8},
  pages={9},
  year={2019}
}

@inproceedings{jia2021scaling,
  title={Scaling up visual and vision-language representation learning with noisy text supervision},
  author={Jia, Chao and Yang, Yinfei and Xia, Ye and Chen, Yi-Ting and Parekh, Zarana and Pham, Hieu and Le, Quoc and Sung, Yun-Hsuan and Li, Zhen and Duerig, Tom},
  booktitle={International Conference on Machine Learning},
  pages={4904--4916},
  year={2021},
  organization={PMLR}
}
@misc{makeascene,
  doi = {10.48550/ARXIV.2203.13131},
  
  url = {https://arxiv.org/abs/2203.13131},
  
  author = {Gafni, Oran and Polyak, Adam and Ashual, Oron and Sheynin, Shelly and Parikh, Devi and Taigman, Yaniv},
  
  keywords = {Computer Vision and Pattern Recognition (cs.CV), Artificial Intelligence (cs.AI), Computation and Language (cs.CL), Graphics (cs.GR), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
  
  title = {Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors},
  
  publisher = {arXiv},
  
  year = {2022},
  
  copyright = {arXiv.org perpetual, non-exclusive license}
}
@misc{dalle1,
  doi = {10.48550/ARXIV.2102.12092},
  
  url = {https://arxiv.org/abs/2102.12092},
  
  author = {Ramesh, Aditya and Pavlov, Mikhail and Goh, Gabriel and Gray, Scott and Voss, Chelsea and Radford, Alec and Chen, Mark and Sutskever, Ilya},
  
  keywords = {Computer Vision and Pattern Recognition (cs.CV), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
  
  title = {Zero-Shot Text-to-Image Generation},
  
  publisher = {arXiv},
  
  year = {2021},
  
  copyright = {Creative Commons Attribution 4.0 International}
}

@article{lafite,
  author    = {Yufan Zhou and
               Ruiyi Zhang and
               Changyou Chen and
               Chunyuan Li and
               Chris Tensmeyer and
               Tong Yu and
               Jiuxiang Gu and
               Jinhui Xu and
               Tong Sun},
  title     = {{LAFITE:} Towards Language-Free Training for Text-to-Image Generation},
  journal   = {CoRR},
  volume    = {abs/2111.13792},
  year      = {2021},
  url       = {https://arxiv.org/abs/2111.13792},
  eprinttype = {arXiv},
  eprint    = {2111.13792},
  timestamp = {Thu, 02 Dec 2021 09:37:06 +0100},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2111-13792.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@misc{hit,
  doi = {10.48550/ARXIV.2106.07631},
  
  url = {https://arxiv.org/abs/2106.07631},
  
  author = {Zhao, Long and Zhang, Zizhao and Chen, Ting and Metaxas, Dimitris N. and Zhang, Han},
  
  keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
  
  title = {Improved Transformer for High-Resolution GANs},
  
  publisher = {arXiv},
  
  year = {2021},
  
  copyright = {arXiv.org perpetual, non-exclusive license}
}

@misc{dfgan,
  doi = {10.48550/ARXIV.2008.05865},
  
  url = {https://arxiv.org/abs/2008.05865},
  
  author = {Tao, Ming and Tang, Hao and Wu, Fei and Jing, Xiao-Yuan and Bao, Bing-Kun and Xu, Changsheng},
  
  keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
  
  title = {DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis},
  
  publisher = {arXiv},
  
  year = {2020},
  
  copyright = {arXiv.org perpetual, non-exclusive license}
}

@misc{dmgan-cl,
  doi = {10.48550/ARXIV.2107.02423},
  
  url = {https://arxiv.org/abs/2107.02423},
  
  author = {Ye, Hui and Yang, Xiulong and Takac, Martin and Sunderraman, Rajshekhar and Ji, Shihao},
  
  keywords = {Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
  
  title = {Improving Text-to-Image Synthesis Using Contrastive Learning},
  
  publisher = {arXiv},
  
  year = {2021},
  
  copyright = {Creative Commons Attribution 4.0 International}
}

@article{attngan,
  author    = {Tao Xu and
               Pengchuan Zhang and
               Qiuyuan Huang and
               Han Zhang and
               Zhe Gan and
               Xiaolei Huang and
               Xiaodong He},
  title     = {AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative
               Adversarial Networks},
  journal   = {CoRR},
  volume    = {abs/1711.10485},
  year      = {2017},
  url       = {http://arxiv.org/abs/1711.10485},
  eprinttype = {arXiv},
  eprint    = {1711.10485},
  timestamp = {Fri, 09 Dec 2022 08:27:30 +0100},
  biburl    = {https://dblp.org/rec/journals/corr/abs-1711-10485.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{zhu2019dm,
  title={Dm-gan: Dynamic memory generative adversarial networks for text-to-image synthesis},
  author={Zhu, Minfeng and Pan, Pingbo and Chen, Wei and Yang, Yi},
  booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
  pages={5802--5810},
  year={2019}
}
@article{dhariwal2021diffusion,
  title={Diffusion models beat gans on image synthesis},
  author={Dhariwal, Prafulla and Nichol, Alexander},
  journal={Advances in Neural Information Processing Systems},
  volume={34},
  pages={8780--8794},
  year={2021}
}

@article{austin2021structured,
  title={Structured denoising diffusion models in discrete state-spaces},
  author={Austin, Jacob and Johnson, Daniel D and Ho, Jonathan and Tarlow, Daniel and van den Berg, Rianne},
  journal={Advances in Neural Information Processing Systems},
  volume={34},
  pages={17981--17993},
  year={2021}
}

@inproceedings{liu2021swin,
  title={Swin transformer: Hierarchical vision transformer using shifted windows},
  author={Liu, Ze and Lin, Yutong and Cao, Yue and Hu, Han and Wei, Yixuan and Zhang, Zheng and Lin, Stephen and Guo, Baining},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={10012--10022},
  year={2021}
}

@article{jouppi2020domain,
  title={A domain-specific supercomputer for training deep neural networks},
  author={Jouppi, Norman P and Yoon, Doe Hyun and Kurian, George and Li, Sheng and Patil, Nishant and Laudon, James and Young, Cliff and Patterson, David},
  journal={Communications of the ACM},
  volume={63},
  number={7},
  pages={67--78},
  year={2020},
  publisher={ACM New York, NY, USA}
}

@inproceedings{shazeer2018adafactor,
  title={Adafactor: Adaptive learning rates with sublinear memory cost},
  author={Shazeer, Noam and Stern, Mitchell},
  booktitle={International Conference on Machine Learning},
  pages={4596--4604},
  year={2018},
  organization={PMLR}
}

@article{hughes2021generative,
  title={Generative Adversarial Networks--Enabled Human--Artificial Intelligence Collaborative Applications for Creative and Design Industries: A Systematic Review of Current Approaches and Trends},
  author={Hughes, Rowan T and Zhu, Liming and Bednarz, Tomasz},
  journal={Frontiers in artificial intelligence},
  volume={4},
  pages={604234},
  year={2021},
  publisher={Frontiers Media SA}
}

@article{franks2018sex,
  title={Sex, lies, and videotape: Deep fakes and free speech delusions},
  author={Franks, Mary Anne and Waldman, Ari Ezra},
  journal={Md. L. Rev.},
  volume={78},
  pages={892},
  year={2018},
  publisher={HeinOnline}
}

@article{whittaker2020all,
  title={“All around me are synthetic faces”: the mad world of AI-generated media},
  author={Whittaker, Lucas and Kietzmann, Tim C and Kietzmann, Jan and Dabirian, Amir},
  journal={IT Professional},
  volume={22},
  number={5},
  pages={90--99},
  year={2020},
  publisher={IEEE}
}

@inproceedings{srinivasan2021biases,
  title={Biases in generative art: A causal look from the lens of art history},
  author={Srinivasan, Ramya and Uchino, Kanji},
  booktitle={Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency},
  pages={41--51},
  year={2021}
}

@inproceedings{steed2021image,
  title={Image representations learned with unsupervised pre-training contain human-like biases},
  author={Steed, Ryan and Caliskan, Aylin},
  booktitle={Proceedings of the 2021 ACM conference on fairness, accountability, and transparency},
  pages={701--713},
  year={2021}
}

@article{paullada2021data,
  title={Data and its (dis) contents: A survey of dataset development and use in machine learning research},
  author={Paullada, Amandalynne and Raji, Inioluwa Deborah and Bender, Emily M and Denton, Emily and Hanna, Alex},
  journal={Patterns},
  volume={2},
  number={11},
  pages={100336},
  year={2021},
  publisher={Elsevier}
}

@mastersthesis{dulhanty2020issues,
  title={Issues in Computer Vision Data Collection: Bias, Consent, and Label Taxonomy},
  author={Dulhanty, Chris},
  year={2020},
  school={University of Waterloo}
}

@article{scheuerman2021datasets,
  title={Do datasets have politics? Disciplinary values in computer vision dataset development},
  author={Scheuerman, Morgan Klaus and Hanna, Alex and Denton, Emily},
  journal={Proceedings of the ACM on Human-Computer Interaction},
  volume={5},
  number={CSCW2},
  pages={1--37},
  year={2021},
  publisher={ACM New York, NY, USA}
}

@article{prabhu2020large,
  title={Large image datasets: A pyrrhic win for computer vision?},
  author={Prabhu, Vinay Uday and Birhane, Abeba},
  journal={arXiv preprint arXiv:2006.16923},
  year={2020}
}

@inproceedings{buolamwini2018gender,
  title={Gender shades: Intersectional accuracy disparities in commercial gender classification},
  author={Buolamwini, Joy and Gebru, Timnit},
  booktitle={Conference on fairness, accountability and transparency},
  pages={77--91},
  year={2018},
  organization={PMLR}
}

@inproceedings{hendricks2018women,
  title={Women also snowboard: Overcoming bias in captioning models},
  author={Hendricks, Lisa Anne and Burns, Kaylee and Saenko, Kate and Darrell, Trevor and Rohrbach, Anna},
  booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
  pages={771--787},
  year={2018}
}

@article{tang2022improved,
  title={Improved Vector Quantized Diffusion Models},
  author={Tang, Zhicong and Gu, Shuyang and Bao, Jianmin and Chen, Dong and Wen, Fang},
  journal={arXiv preprint arXiv:2205.16007},
  year={2022}
}

@article{Loshchilov2017FixingWD,
  title={Fixing Weight Decay Regularization in {A}dam},
  author={Ilya Loshchilov and Frank Hutter},
  journal={preprint arXiv:1711.05101},
  year={2017},
}

@inproceedings{Loshchilov2017SGDRSG,
  title={{SGDR}: Stochastic Gradient Descent with Warm Restarts},
  author={Ilya Loshchilov and Frank Hutter},
  booktitle="iclr",
  year={2017}
}

@article{Goyal2017AccurateLM,
  title={Accurate, Large Minibatch {SGD}: Training {I}mage{N}et in 1 Hour},
  author={Priya Goyal and Piotr Doll{\'a}r and Ross B. Girshick and Pieter Noordhuis and Lukasz Wesolowski and Aapo Kyrola and Andrew Tulloch and Yangqing Jia and Kaiming He},
  journal={preprint arXiv:1706.0267},
  year={2017},
}

@misc{negprompt,
    author = "{NegPrompt}",
    title = "Negative Prompt",
    year = "2022",
    url = "https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Negative-prompt",
}

@misc{sdinference,
    author = "{Lambda Labs}",
    title = "All You Need Is One GPU: Inference Benchmark For Stable Diffusion",
    year = "2022",
    url = "https://lambdalabs.com/blog/inference-benchmark-stable-diffusion",
}


@misc{sdgeneration,
    author = "{CompVis}",
    title = "Stable Diffusion Colab",
    year = "2022",
    url = "https://colab.sandbox.google.com/github/huggingface/notebooks/blob/main/diffusers/stable_diffusion.ipynb#scrollTo=zHkHsdtnry57",
}

@inproceedings{KingmaB14,
  author    = {Diederik P. Kingma and
               Jimmy Ba},
  title     = {Adam: {A} Method for Stochastic Optimization},
  booktitle = {{ICLR}},
  year      = {2015},
}
  
% image editing
@inproceedings{li2020manigan,
  title={Manigan: Text-guided image manipulation},
  author={Li, Bowen and Qi, Xiaojuan and Lukasiewicz, Thomas and Torr, Philip HS},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={7880--7889},
  year={2020}
}
@article{gal2022stylegan,
  title={Stylegan-nada: Clip-guided domain adaptation of image generators},
  author={Gal, Rinon and Patashnik, Or and Maron, Haggai and Bermano, Amit H and Chechik, Gal and Cohen-Or, Daniel},
  journal={ACM Transactions on Graphics (TOG)},
  volume={41},
  number={4},
  pages={1--13},
  year={2022},
  publisher={ACM New York, NY, USA}
}
@inproceedings{patashnik2021styleclip,
  title={Styleclip: Text-driven manipulation of stylegan imagery},
  author={Patashnik, Or and Wu, Zongze and Shechtman, Eli and Cohen-Or, Daniel and Lischinski, Dani},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={2085--2094},
  year={2021}
}
@inproceedings{kim2022diffusionclip,
  title={DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation},
  author={Kim, Gwanghyun and Kwon, Taesung and Ye, Jong Chul},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={2426--2435},
  year={2022}
}

@inproceedings{salimans2022distillation,
  author    = {Tim Salimans and
               Jonathan Ho},
  title     = {Progressive Distillation for Fast Sampling of Diffusion Models},
  booktitle = {{ICLR}},
  year      = {2022},
}

@article{Zhu2022dpm,
  author    = {Cheng Lu and
               Yuhao Zhou and
               Fan Bao and
               Jianfei Chen and
               Chongxuan Li and
               Jun Zhu},
  title     = {DPM-Solver: {A} Fast {ODE} Solver for Diffusion Probabilistic Model
               Sampling in Around 10 Steps},
  journal={arXiv preprint arXiv:2206.00927},
  year      = {2022},
}

@article{esser2021imagebart,
  title={Imagebart: Bidirectional context with multinomial diffusion for autoregressive image synthesis},
  author={Esser, Patrick and Rombach, Robin and Blattmann, Andreas and Ommer, Bjorn},
  journal={Advances in Neural Information Processing Systems},
  volume={34},
  pages={3518--3532},
  year={2021}
}

@misc{nulltext2022,
  doi = {10.48550/ARXIV.2211.09794},
  url = {https://arxiv.org/abs/2211.09794},
  author = {Mokady, Ron and Hertz, Amir and Aberman, Kfir and Pritch, Yael and Cohen-Or, Daniel},
  title = {Null-text Inversion for Editing Real Images using Guided Diffusion Models},
  publisher = {arXiv},
  year = {2022}
}

@misc{diffusers,
  author = {Patrick von Platen and Suraj Patil and Anton Lozhkov and Pedro Cuenca and Nathan Lambert and Kashif Rasul and Mishig Davaadorj and Thomas Wolf},
  title = {Diffusers: State-of-the-art diffusion models},
  year = {2022},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/huggingface/diffusers}}
}

@misc{sdedit,
  doi = {10.48550/ARXIV.2108.01073},
  url = {https://arxiv.org/abs/2108.01073},
  author = {Meng, Chenlin and He, Yutong and Song, Yang and Song, Jiaming and Wu, Jiajun and Zhu, Jun-Yan and Ermon, Stefano},
  title = {SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations},
  publisher = {arXiv},
  year = {2021}
}

@article{lee2022draft,
  title={Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformer},
  author={Lee, Doyup and Kim, Chiheon and Kim, Saehoon and Cho, Minsu and Han, Wook-Shin},
  journal={arXiv preprint arXiv:2206.04452},
  year={2022}
}

@inproceedings{lee2022autoregressive,
  title={Autoregressive Image Generation using Residual Quantization},
  author={Lee, Doyup and Kim, Chiheon and Kim, Saehoon and Cho, Minsu and Han, Wook-Shin},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={11523--11532},
  year={2022}
}

@article{brooks2022instructpix2pix,
  title={InstructPix2Pix: Learning to Follow Image Editing Instructions},
  author={Brooks, Tim and Holynski, Aleksander and Efros, Alexei A},
  journal={arXiv preprint arXiv:2211.09800},
  year={2022}
}

@article{meng2021sdedit,
  title={Sdedit: Image synthesis and editing with stochastic differential equations},
  author={Meng, Chenlin and Song, Yang and Song, Jiaming and Wu, Jiajun and Zhu, Jun-Yan and Ermon, Stefano},
  journal={arXiv preprint arXiv:2108.01073},
  year={2021}
}

@article{xia2022gan,
  title={Gan inversion: A survey},
  author={Xia, Weihao and Zhang, Yulun and Yang, Yujiu and Xue, Jing-Hao and Zhou, Bolei and Yang, Ming-Hsuan},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2022},
  publisher={IEEE}
}

@misc{imageneditor,
  doi = {10.48550/ARXIV.2212.06909},
  url = {https://arxiv.org/abs/2212.06909},
  author = {Wang, Su and Saharia, Chitwan and Montgomery, Ceslee and Pont-Tuset, Jordi and Noy, Shai and Pellegrini, Stefano and Onoe, Yasumasa and Laszlo, Sarah and Fleet, David J. and Soricut, Radu and Baldridge, Jason and Norouzi, Mohammad and Anderson, Peter and Chan, William},
  title = {Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting},
  publisher = {arXiv},
  year = {2022},
}